Abnormal behavior detection for early warning of terrorist attack

Authors:
Xin Geng;Gang Li;Yangdong Ye;Yiqing Tu;Honghua Dai
Affiliations:
School of Engineering and Information Technology, Deakin University, VIC, Australia;School of Engineering and Information Technology, Deakin University, VIC, Australia;School of Information Engineering, Zhengzhou University, Zhengzhou, China;School of Engineering and Information Technology, Deakin University, VIC, Australia;School of Engineering and Information Technology, Deakin University, VIC, Australia
Venue:
AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence
Year:
2006

Citing 2
Cited 1

Normalized Cuts and Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision

Abnormal human behavioral pattern detection in assisted living environments

Proceedings of the 3rd International Conference on PErvasive Technologies Related to Assistive Environments

Quantified Score

Hi-index	0.00

Visualization

Abstract

Many terrorist attacks are accomplished by bringing explosive devices hidden in ordinary-looking objects to public places. In such case, it is almost impossible to distinguish a terrorist from ordinary people just from the isolated appearance. However, valuable clues might be discovered through analyzing a series of actions of the same person. Abnormal behaviors of object fetching, deposit, or exchange in public places might indicate potential attacks. Based on the widely equipped CCTV surveillance systems at the entrance of many public places, this paper proposes an algorithm to detect such abnormal behaviors for early warning of terrorist attack.